Effect of DropBlock and RFB block

[sidml]

Hi. Thanks for sharing the code.

I had two questions. In section 4.4 of the paper you mentioned that ,

final model is YOLOv3 with ASFF*, which is an enhancedASFFversion by integrating other lightweight modules (i.e.DropBlock [7] and RFB [23]) with 1.5×longer training timethan the models in Section 4.1.

1. How is the final model (YOLOv3 with ASFF*) performance without DropBlock and RFB modules.
2. How is the model (YOLOv3 baseline) performance with DropBlock and RFB modules.

This will help us in understanding the performance improvement due to ASFF block more clearly. Thanks.

[GOATmessi7]

Thanks for your suggestion! 1.5x longer training (450-500 epochs) will consume about 2 weeks on 10 2080ti, which is unavailable for me now. The purpose of training the ASFF* model is only to get better performance, and I have done one additional experiment that the yolov3 baseline with rfb module can get 39.8 mAP.